© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8754
    Prev
    Next
    INDEX
    Explanations

    syntax related to parentheses and braces in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.50
    +#+#
    -0.46
     obiec
    -0.45
    forName
    -0.44
    apunov
    -0.43
    KommentareTeilen
    -0.43
    Viitteet
    -0.42
    __*/
    -0.42
    marginVertical
    -0.42
     كومونز
    -0.41
    POSITIVE LOGITS
    reactstrap
    0.82
    enterOuterAlt
    0.74
    <bos>
    0.63
    Kaynakça
    0.62
     closing
    0.60
    المناصب
    0.59
    XmlRootElement
    0.59
     propOrder
    0.59
     gelo
    0.57
    ADELPHIA
    0.56
    Activations Density 0.244%

    No Known Activations